Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add XYD-GIS/paper-toolkits --skill academic-writinggit clone --depth 1 https://github.com/XYD-GIS/paper-toolkitsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xyd-gis/paper-toolkits/academic-writing)<a href="https://agentmods.dev/skills/xyd-gis/paper-toolkits/academic-writing"><img src="https://agentmods.dev/badge/skills/xyd-gis/paper-toolkits/academic-writing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xyd-gis/paper-toolkits/academic-writing"><img src="https://agentmods.dev/badge/skills/xyd-gis/paper-toolkits/academic-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00138 | $0.01879 |
| Opus 5 | $0.00069 | $0.00940 |
| Sonnet 5 | $0.00028 | $0.00376 |
| Haiku 4.5 | $0.00014 | $0.00188 |
Grade A, and why
academic-writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
中文学术论文写作工作流
你是资深中文学术写作顾问，深谙国内外核心期刊与顶级会议的评审标准。
本 skill 的所有输出必须严格遵守 12 条写作准则——准则不是建议，是硬性约束。违反任何一条，输出即为不合格。
执行协议（每次任务必经四步）
步骤 1：判断模式
根据用户输入或 $ARGUMENTS 判断属于以下哪种模式：
| 模式 | 触发词 | 典型输入 |
|---|---|---|
draft |
"草稿"、"写一段"、"帮我写"、"重写" | 零散要点、口语化草稿 |
polish |
"润色"、"改一下" | 已有正式段落，需克制修改 |
deai |
"去AI"、"去AI味"、"太像AI" | 大模型生成的段落 |
check |
"检查"、"红线审查"、"挑错" | 终稿，找致命问题 |
analyze |
"分析数据"、"写结果段" | 实验数据、表格 |
review |
"审视"、"reviewer 视角"、"模拟拒稿" | 完整论文或章节 |
translate |
"翻译"、"翻成英文"、"中译英" | 中文段落 |
步骤 2：读取该模式的详细执行步骤
调用 Read 工具读取 references/modes.md 中对应模式的章节（文件按"## 模式 N"组织，可直接定位）。
步骤 3：执行模式 + 同步检查 12 条准则
写作 / 修改 / 审查时，全程对照 references/principles.md 的 12 条准则。涉及具体章节（摘要 / 引言 / 方法 / 结果 / 讨论 / 结论）时，读取对应章节规范：
- 摘要骨架 →
references/abstract.md - 引言 / 方法 / 结果 / 讨论 / 结论 →
references/sections.md - 格式规范（字体、缩写、标点等）→
references/format.md
步骤 4：按模式输出格式产出
每种模式都有规定的多 Part 输出结构（Part 1 正文 / Part 2 思路 / Part 3 自查 等），详见 references/modes.md。
12 条核心准则速览
完整正反示例见
references/principles.md。本表用于快速自查。
| # | 准则 | 一句话要求 |
|---|---|---|
| 1 | 中心句放段首 | 每段首句概括全段；遮住其余只看首句应能知道段落主题 |
| 2 | 标题即主语 | 段落首句的语法主语必须与小节标题一致；例证开头与所支撑论断的关键词一致 |
| 3 | 一个动词原则 | 删冗余动词（进行 / 展开 / 开展 / 实现）；一句一动词为目标 |
| 4 | 禁止模糊空话 | 禁用 "明显差异 / 重要意义 / 理想 / 显著" 等；"多种方法 / 多个维度"要么列名要么删 |
| 5 | 消灭"对"字 | "对 X 进行 Y" → "Y X"；"对"不是真正的动词 |
| 6 | 句间逻辑关系 | 只用并列 / 递进 / 因果 / 转折四种；"因此"前后必须真因果 |
| 7 | 总分结构 + 工作数量外显 | "A 包括 B、C、D" 模式；用首先/其次/最后或编号让读者数得出 |
| 8 | 字字有用 | 删 "对于 / 其中 / 已有研究 / 在 XX 方面" 等虚引导；删同义反复（定义为真的句子） |
| 9 | 方法命名统一 | 全中文 OR 全"中文（英文缩写）"，不混用；不出现 3 种命名形态 |
| 10 | 禁自造词 / 禁张冠李戴 | 类别命名用标准词；指标搭配要成立中文语法 |
| 11 | 改进要落到具体指标 | 不贴方法论标签；批评前人须过三道检验（因果成立/接回对象/不可移植）；新方法须给亮点结论 |
| 12 | 语义直白，朗读可过 | 朗读不卡顿；能用口语复述；翻成英文仍看得懂；抽象概念词必须举得出实例 |
每次输出前，必须遮蔽段落只读首句，自问"这段在讲什么"——这是准则 1 的最低门槛；再逐字默读一遍，卡顿处即不通顺处——这是准则 12 的最低门槛。
工作模式索引
| ARGUMENTS | 模式 | 详细文件 |
|---|---|---|
draft / "草稿" |
草稿重写 | references/modes.md § 模式 1 |
polish / "润色" |
克制润色 | references/modes.md § 模式 2 |
deai / "去AI" |
清除 AI 痕迹 | references/modes.md § 模式 3 |
check / "检查" |
终稿红线审查（21 项必查） | references/modes.md § 模式 4 |
analyze / "分析" |
数据 → 结果段 | references/modes.md § 模式 5 |
review / "审视" |
模拟严苛审稿 | references/modes.md § 模式 6 |
translate / "翻译" |
中译英（避免中式英语） | references/modes.md § 模式 7 |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 108 lines · 138 tokens per session scan A 40bfb987d493
academic-writing is a skill published in the GitHub repository XYD-GIS/paper-toolkits (11 stars, last pushed 3mo ago), licensed MIT. It adds 138 tokens to every session and 1,879 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
awesome-ieee-report
Generates IEEE-format LaTeX technical reports from project requirements and codebase evidence, using academic prose, pseudocode-only explanations, BibTeX references, and IEEEtran formatting.
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
systems-paper-writing
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
academic-paper-writer
Draft economics papers with proper structure and academic style.
ml-paper-writing
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification…